論文 ·日本語 ·未確認

A System to Generate Onomatopoeia Corresponding to User^|^apos;s Impressions

Yuichiro Shimizu Ryuichi Doizaki Tatsuki Kagitani Maki Sakamoto

刊行年
2015-01-01
収録
『Transactions of the Japanese Society for Artificial Intelligence』 30(1) pp. 319-330
出版
The Japanese Society for Artificial Intelligence
言語
英語
openalex
W2329122444
doi
10.1527/tjsai.30.319
mag
2329122444
issn
1346-0714
URL
https://www.jstage.jst.go.jp/article/tjsai/30/1/30_30_319/_pdf

要旨

The present study proposes a method which generates Japanese onomatopoeia corresponding to impressions inputted by users. Japanese onomatopoeia is frequently used in comics and advertisements. Effective onomatopoeia in those fields are directly associated with sensuous experiences of readers or consumers, but it is very difficult to create such expressions. Therefore, the system which generates effective novel onomatopoeia corresponding to the impression specified by users has been expected to be as a technology which supports creators. Our system uses 43 SD scales as those expressing our intuitive impressions. These scales consist of scales expressing impressions of a haptic senses, visual senses and affective senses. Users of the system can choose the kinds of SD scales to be used to create onomatopoeia among from 1 to 43 SD scales. The system uses the genetic algorithm (GA) to create onomatopoeia corresponding to inputted impressions. We consider onomatopoeic expressions as a individuals of GA, which are expressed by an array of numerical values. Namely, each numerical value of an individual denotes each phonological symbol in Japanese. By comparing impressions inputted by user with those of each generated onomatopoeia, the system proposes onomatopoeia corresponding to impressions of users. The system evaluation showed that impressions of onomatopoeic expressions generated by our system were similar to the impressions inputted by users.

主題

この書誌の出所

  • openalex— W2329122444(2026-08-12取得)

引用キー: Shimizu2015SystemGenerateOnomatopoeia

書誌 34,896件 語別索引 17,251件 資源 113件 研究者 303名 JSON